You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"Total per-feed row emissions per batch (the wire-value serializations the current path performs). Divide by realtime_native.emission_distinct_serializations for average feeds-per-run fan-out; the excess is duplicate serialization a serialize-once-per-batch memo would remove.",
"Matched (feed,run) rows resolved to feeds per batch, summed. Upper bound on per-feed wire serializations, since the client working-set diff drops already-seen rows before encoding. Divide by realtime_native.emission_distinct_runs for average feeds-per-run fan-out.",
"Distinct (columnSig,runId) emitted per batch, summed. A serialize-once-per-batch memo would perform exactly this many serializations vs realtime_native.emission_run_serializations today; 1 - (this / run_serializations) is the memo's serialization-work saving.",
"Distinct (columnSig,run) among the deliveries per batch, summed. The serialize-once-per-batch floor: a shared-serialization step would encode at most this many rows, saving at most (feed_deliveries minus distinct_runs) encodings.",
0 commit comments